SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.07241 · CVPR · 2024

Calibrating Multi-modal Representations: A Pursuit of Group Robustness without Annotations

Yifei Min, Chenyu You, James Duncan, Weicheng Dai, Lawrence Staib, Jasjeet Sekhon

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2403.07241.json · badge: /api/ran/2403.07241.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
charlesyou999648/cfr canonical (classifier label)
classifier basis: census
1 ran · 2 no recorded run
FunctionStatusWhere it lives
infer_d_out Ran
ran, honoured the contract we drafted
charlesyou999648/cfr/code/algorithms/initializer.py
code served (permissive licence) · get_code("c7c45c9d089b1f01")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

class MockDataset:
    def __init__(self, is_classification=False, is_detection=False, y_size=None, n_classes=None):
        self.is_classification = is_classification
        self.is_detection = is_detection
        self.y_size = y_size
        self.n_classes = n_classes

class MockConfig:
    def __init__(self, algorithm='some_algorithm'):
        self.algorithm = algorithm

# Test case 1: classification with y_size == 1
train_dataset_1 = MockDataset(
    is_classification=True,
    is_detection=False,
    y_size=1,
    n_classes=5
)
config_1 = MockConfig(algorithm='standard')

# Use the first case for ARGS
ARGS = {
    'train_dataset': train_dataset_1,
    'config': config_1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_dataset_class Not yet run
unverified (harvested, no recorded run)
charlesyou999648/cfr/code/dataset.py
code served (permissive licence) · get_code("5b0092cb7767b24c")
How it ran

no invocation recorded.

num_environments Not yet run
unverified (harvested, no recorded run)
charlesyou999648/cfr/code/dataset.py
code served (permissive licence) · get_code("38ace74bf6716b77")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 2 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
num_environments 21 other papers
17 dated earlier, 1 the same month, 3 later
1907.02893 (2019-07)
Invariant Risk Minimization
2007.01434 (2020-07)
In Search of Lost Domain Generalization
2106.02266 (2021-06)
SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization
and 18 more not named here
get_dataset_class 3 other papers
1 dated earlier, 2 later
2302.12254 (2023-02)
Change is Hard: A Closer Look at Subpopulation Shift
2603.25839 (2026-03)
A Compression Perspective on Simplicity Bias
2606.00082 (2026-06)
Hoeffding Concept Bottleneck Models with Applications to Overhead Images

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Fine-tuning pre-trained vision-language models, like CLIP, has yielded success on diverse downstream tasks. However, several pain points persist for this paradigm: (i) directly tuning entire pre-trained models becomes both timeintensive and computationally costly. Additionally, these tuned models tend to become highly specialized, limiting their practicality for real-world deployment; (ii) recent studies indicate that pre-trained vision-language classifiers may overly depend on spurious features -patterns that correlate with the target in training data, but are not related to the true labeling function; and (iii) existing studies on mitigating the reliance on spurious features, largely based on the assumption that we can identify such features, does not provide definitive assurance for real-world applications. As a piloting study, this work focuses on exploring mitigating the reliance on spurious features for CLIP without using any group annotation. To this end, we systematically study the existence of spurious correlation on CLIP and CILP+ERM. We first, following recent work on Deep Feature Reweighting (DFR), verify that last-layer retraining can greatly improve group robustness on pretrained CLIP. In view of them, we advocate a lightweight representation calibration method for fine-tuning CLIP, by first generating a calibration set using the pretrained CLIP, and then calibrating representations of samples within this set through contrastive learning, all without the need for group labels. Extensive experiments and in-depth visualizations on several benchmarks validate the effectiveness of our proposals, largely reducing reliance and significantly boosting the model generalization. Our codes will be available in here

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.07241")
get_code_for_paper("2403.07241")
have("2403.07241")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2403.07241.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2403.07241.svg)](https://syntology.ai/paper/2403.07241)

Connect an agent — have() is free.